Evaluation of Global Land Use–Land Cover Data Products in Guangxi, China

Land use–land cover (LULC) is an important feature for ecological environment research, land resource management and evaluation. Although global high-resolution LULC data sets are booming, their regional performances were still evaluated in limited regions. To demonstrate the local applicability of products, six emerging products compared Guangxi, China. The used European Space Agency GlobCover (ESAGC), ESRI Use–Land Cover (ESRI–LULC), Finer Resolution Observation Monitoring Global (FROM–GLC), China Dataset (CLCD), product with Fine Classification System at 30 m (GLC_FCS30) GlobeLand30 (GLC30). Reference obtained from government statistical yearbook remote sensing images on Google Earth. results showed that CLCD, ESRI–LULC GLC30 found to agree well forest reference data, highest correlation coefficient 0.999. For cropland areas, GLC30, CLCD ESAGC agreed was 0.957. Combined comparison by Earth, we finally concluded ESAGC, can best represent LULCs Guangxi. Furthermore, spatial consistency analysis three or more identified same type as high 96.98% area. We suggest majority voting might be applied provide fused better a scale avoid error caused single product.